shubhamdikshit

developed and planned automation test scripts in java using selenium framework as part of ci/cd pipeline using jenkins. coordinated closely with project managers and team members to ensure automation solutions met project requirements and deadlines. set up active directory federation service, giving client computers sso access to the blueworkslive service. collaborated with cross-functional teams to identify opportunities for automation and improve existing processes. created manual test cases, conducted code reviews and verified bug fixes using rationalteam concert (rtc) and rational quality manager (rqm) for version control. developed code to manipulate data to prepare for reporting and workflow activities. performed assigned tasks of maintaining the front-end (html, css, javascript) and back-end (java and sql) code.

collected the data through an online survey and performed an analysis of survey data which helped the r&d teams. built monthly executive reports and ad-hoc requests outlining sales, consumer behavior and industry trends to give insights to the management. collaborated with colleagues on implementation of data-driven marketing strategies which significantly increased sales and brand awareness.

constructed an explainable artificial intelligence (xai) model for sarcasm detection in dialogues, achieving an accuracy of 95% on the mustard dataset. developed a pipeline employing a diverse range of algorithms, including ensemble models, kernel-based models, decision trees, and regression models, to assess their accuracy in decision-making. applied the xgboost machine learning algorithm to analyze a dataset comprising 690 dialogues from the mustard dataset, achieving an accuracy of 90%. applied lime and shap explainability techniques to enhance the performance of the xgboost algorithm, resulting in a notable 5% increase in accuracy to 95%.

executed language translation of low resourced indian languages using seq2seq model using pytorch. improved bleu scores by 10% for tamil (5.43), telugu (4.97) and bengali (4.07) languages. used attention decoder to obtain features. trained and deployed the model using pytorch.